io.github.eltociear/contract-guard-mcp
EVM contract/token risk check + ERC20 approval (proxy, EIP-7702, unlimited-allowance). Zero deps.
What can you do with io.github.eltociear/contract-guard-mcp?
check_contract(address, chain)— is-contract/EOA, EIP-7702, proxy, ERC20 metadata, risk scorecheck_approval(token, owner, spender, chain)— ERC20 allowance audit; flags unlimited approvals (the #1 drain vector)
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
ghcr.io/eltociear/contract-guard-mcp:mcp-1.1.0claude mcp add contract-guard-mcp -- docker run -i --rm ghcr.io/eltociear/contract-guard-mcp:mcp-1.1.0
{
"mcpServers": {
"contract-guard-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/eltociear/contract-guard-mcp:mcp-1.1.0"
]
}
}
}
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
contract-guard-mcp
MCP server for a pre-interaction risk check on any EVM contract/token — what an agent needs before it approves, swaps, or trusts an address.
Tool: check_contract(address, chain="base") →
- is-contract vs EOA / self-destructed
- EIP-7702 delegated-EOA detection
- upgradeable proxy detection (EIP-1967 + legacy zeppelinos)
- ERC20 metadata (name / symbol / decimals / totalSupply)
- risk score + actionable flags
Chains: Base, Ethereum. Pure public JSON-RPC, zero dependencies, no signing.
Also available as a pay-per-call x402 HTTP endpoint:
https://eltociear-contract-guard.hf.space (POST /check, $0.005 USDC on Base).
Run
docker run -i --rm ghcr.io/eltociear/contract-guard-mcp:mcp-latest
# or
python3 server.py
MIT licensed.
Tools
check_contract(address, chain)— is-contract/EOA, EIP-7702, proxy, ERC20 metadata, risk scorecheck_approval(token, owner, spender, chain)— ERC20 allowance audit; flags unlimited approvals (the #1 drain vector)
Free MCP vs paid x402
This MCP server is free (run it locally / via your client). For server-side, batch, or no-install use, the same engine is a pay-per-call x402 HTTP API — POST https://eltociear-contract-guard.hf.space/check ($0.005 USDC on Base, no signup). Your agent's wallet pays per call.
Professional audit services
Maintained by the same author — paid services on Polar (Stripe checkout):
- MCP Security Audit Report — $5 — one-off audit of your MCP server: 68 attack patterns, severity-rated PDF report with concrete fixes.
- Security Pulse — $5/mo (annual $50) — monthly briefing on newly disclosed MCP server vulnerabilities, scan stats across 100+ tracked repos, mitigation playbooks.
- Pro Audit Stack — $20/mo — for teams running MCP servers in CI/CD: 50 hosted scans/month, Discord access, 24h SLA on vulnerability questions.
Full catalog: polar.sh/eltociear
Also live: clean-read ($0.005 / call)
Same operator, same x402 rails: clean-read turns any URL into clean Markdown for AI agents — fetches the page, strips nav/ads/boilerplate (trafilatura), returns the main content with title and word count. POST https://eltociear-skill-audit.hf.space/read — $0.005 USDC on Base, no signup.
Frequently asked questions
What is io.github.eltociear/contract-guard-mcp?
EVM contract/token risk check + ERC20 approval (proxy, EIP-7702, unlimited-allowance). Zero deps.
How do I install io.github.eltociear/contract-guard-mcp?
It runs on your machine. In Claude Code: claude mcp add contract-guard-mcp -- docker run -i --rm ghcr.io/eltociear/contract-guard-mcp:mcp-1.1.0. For other clients, paste the JSON configuration from this page into their MCP settings.
Does io.github.eltociear/contract-guard-mcp need an API key?
Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.
Is io.github.eltociear/contract-guard-mcp open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains io.github.eltociear/contract-guard-mcp?
It is published by eltociear. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.